method · first seen 5 Oct 2026
multi-turn reinforcement learning
Also: multi-turn RL
Reinforcement learning over full multi-step dialogue trajectories rather than single responses.
Mentions per week
PapersCodeDiscussion
Earliest sources
- The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement LearningPapers · 5 Oct 2026 · Jakub Macina, Manu Kapur, Mrinmaya Sachan
- MIMESIS: Learning User Simulators as Training Environments for Interactive AgentsPapers · 7 Oct 2026 · Hoang Phan, Dat Huynh, Andrey Zhmoginov, Qi Zeng, Wancen Mu, Yue Cao, Shengjie B…
- C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement LearningPapers · 14 Oct 2026 · Ai Jian, Haoran Pan, Eryu Guo, Haojin Yang, Jinghan He, Xiaoyun Zhang, Jiangbo P…
- xinxinliu-ai/AgenticRoboRLCode · 16 Oct 2026 · xinxinliu-ai · 72 stars
- AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic RoboticsPapers · 20 Oct 2026 · Xinxin Liu, Bingxin Xu, Wenrui Bao, Ming Li, Wentao Bao, Chen Chen, Yuzhang Shan…
- CaPtain: A Pipeline for Post-Training Code-as-Policy Robot AgentsPapers · 29 Oct 2026 · Yijia Fan, Xilin He, Yilei Jiang, Dongming Wu, Jiaxu Wang, Xiangyu Yue
Latest sources
- Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game AgentPapers · 13 Nov 2026 · Run Luo, Kuan Zhang, Qi Deng, Yukun Chen, Zhihao Yang, Yufei Zhang, Renrong Hu,…
- CaPtain: A Pipeline for Post-Training Code-as-Policy Robot AgentsPapers · 29 Oct 2026 · Yijia Fan, Xilin He, Yilei Jiang, Dongming Wu, Jiaxu Wang, Xiangyu Yue
- AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic RoboticsPapers · 20 Oct 2026 · Xinxin Liu, Bingxin Xu, Wenrui Bao, Ming Li, Wentao Bao, Chen Chen, Yuzhang Shan…
- xinxinliu-ai/AgenticRoboRLCode · 16 Oct 2026 · xinxinliu-ai · 72 stars
- C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement LearningPapers · 14 Oct 2026 · Ai Jian, Haoran Pan, Eryu Guo, Haojin Yang, Jinghan He, Xiaoyun Zhang, Jiangbo P…
- MIMESIS: Learning User Simulators as Training Environments for Interactive AgentsPapers · 7 Oct 2026 · Hoang Phan, Dat Huynh, Andrey Zhmoginov, Qi Zeng, Wancen Mu, Yue Cao, Shengjie B…
- The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement LearningPapers · 5 Oct 2026 · Jakub Macina, Manu Kapur, Mrinmaya Sachan